summaryrefslogtreecommitdiff
path: root/hw/i386/kvm/pci-assign.c
blob: ff33dc8850d17ac9b2a8bafed282f46a24a44f5a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
/*
 * Copyright (c) 2007, Neocleus Corporation.
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 *
 *  Assign a PCI device from the host to a guest VM.
 *
 *  This implementation uses the classic device assignment interface of KVM
 *  and is only available on x86 hosts. It is expected to be obsoleted by VFIO
 *  based device assignment.
 *
 *  Adapted for KVM (qemu-kvm) by Qumranet. QEMU version was based on qemu-kvm
 *  revision 4144fe9d48. See its repository for the history.
 *
 *  Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com)
 *  Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com)
 *  Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com)
 *  Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com)
 *  Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com)
 */
#include <stdio.h>
#include <unistd.h>
#include <sys/io.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
#include "hw/hw.h"
#include "hw/i386/pc.h"
#include "qemu/error-report.h"
#include "ui/console.h"
#include "hw/loader.h"
#include "monitor/monitor.h"
#include "qemu/range.h"
#include "sysemu/sysemu.h"
#include "hw/pci/pci.h"
#include "hw/pci/msi.h"
#include "kvm_i386.h"

#define MSIX_PAGE_SIZE 0x1000

/* From linux/ioport.h */
#define IORESOURCE_IO       0x00000100  /* Resource type */
#define IORESOURCE_MEM      0x00000200
#define IORESOURCE_IRQ      0x00000400
#define IORESOURCE_DMA      0x00000800
#define IORESOURCE_PREFETCH 0x00002000  /* No side effects */
#define IORESOURCE_MEM_64   0x00100000

//#define DEVICE_ASSIGNMENT_DEBUG

#ifdef DEVICE_ASSIGNMENT_DEBUG
#define DEBUG(fmt, ...)                                       \
    do {                                                      \
        fprintf(stderr, "%s: " fmt, __func__ , __VA_ARGS__);  \
    } while (0)
#else
#define DEBUG(fmt, ...)
#endif

typedef struct PCIRegion {
    int type;           /* Memory or port I/O */
    int valid;
    uint64_t base_addr;
    uint64_t size;    /* size of the region */
    int resource_fd;
} PCIRegion;

typedef struct PCIDevRegions {
    uint8_t bus, dev, func; /* Bus inside domain, device and function */
    int irq;                /* IRQ number */
    uint16_t region_number; /* number of active regions */

    /* Port I/O or MMIO Regions */
    PCIRegion regions[PCI_NUM_REGIONS - 1];
    int config_fd;
} PCIDevRegions;

typedef struct AssignedDevRegion {
    MemoryRegion container;
    MemoryRegion real_iomem;
    union {
        uint8_t *r_virtbase; /* mmapped access address for memory regions */
        uint32_t r_baseport; /* the base guest port for I/O regions */
    } u;
    pcibus_t e_size;    /* emulated size of region in bytes */
    pcibus_t r_size;    /* real size of region in bytes */
    PCIRegion *region;
} AssignedDevRegion;

#define ASSIGNED_DEVICE_PREFER_MSI_BIT  0
#define ASSIGNED_DEVICE_SHARE_INTX_BIT  1

#define ASSIGNED_DEVICE_PREFER_MSI_MASK (1 << ASSIGNED_DEVICE_PREFER_MSI_BIT)
#define ASSIGNED_DEVICE_SHARE_INTX_MASK (1 << ASSIGNED_DEVICE_SHARE_INTX_BIT)

typedef struct MSIXTableEntry {
    uint32_t addr_lo;
    uint32_t addr_hi;
    uint32_t data;
    uint32_t ctrl;
} MSIXTableEntry;

typedef enum AssignedIRQType {
    ASSIGNED_IRQ_NONE = 0,
    ASSIGNED_IRQ_INTX_HOST_INTX,
    ASSIGNED_IRQ_INTX_HOST_MSI,
    ASSIGNED_IRQ_MSI,
    ASSIGNED_IRQ_MSIX
} AssignedIRQType;

typedef struct AssignedDevice {
    PCIDevice dev;
    PCIHostDeviceAddress host;
    uint32_t dev_id;
    uint32_t features;
    int intpin;
    AssignedDevRegion v_addrs[PCI_NUM_REGIONS - 1];
    PCIDevRegions real_device;
    PCIINTxRoute intx_route;
    AssignedIRQType assigned_irq_type;
    struct {
#define ASSIGNED_DEVICE_CAP_MSI (1 << 0)
#define ASSIGNED_DEVICE_CAP_MSIX (1 << 1)
        uint32_t available;
#define ASSIGNED_DEVICE_MSI_ENABLED (1 << 0)
#define ASSIGNED_DEVICE_MSIX_ENABLED (1 << 1)
#define ASSIGNED_DEVICE_MSIX_MASKED (1 << 2)
        uint32_t state;
    } cap;
    uint8_t emulate_config_read[PCI_CONFIG_SPACE_SIZE];
    uint8_t emulate_config_write[PCI_CONFIG_SPACE_SIZE];
    int msi_virq_nr;
    int *msi_virq;
    MSIXTableEntry *msix_table;
    hwaddr msix_table_addr;
    uint16_t msix_max;
    MemoryRegion mmio;
    char *configfd_name;
    int32_t bootindex;
} AssignedDevice;

static void assigned_dev_update_irq_routing(PCIDevice *dev);

static void assigned_dev_load_option_rom(AssignedDevice *dev);

static void assigned_dev_unregister_msix_mmio(AssignedDevice *dev);

static uint64_t assigned_dev_ioport_rw(AssignedDevRegion *dev_region,
                                       hwaddr addr, int size,
                                       uint64_t *data)
{
    uint64_t val = 0;
    int fd = dev_region->region->resource_fd;

    if (fd >= 0) {
        if (data) {
            DEBUG("pwrite data=%" PRIx64 ", size=%d, e_phys=" TARGET_FMT_plx
                  ", addr="TARGET_FMT_plx"\n", *data, size, addr, addr);
            if (pwrite(fd, data, size, addr) != size) {
                error_report("%s - pwrite failed %s",
                             __func__, strerror(errno));
            }
        } else {
            if (pread(fd, &val, size, addr) != size) {
                error_report("%s - pread failed %s",
                             __func__, strerror(errno));
                val = (1UL << (size * 8)) - 1;
            }
            DEBUG("pread val=%" PRIx64 ", size=%d, e_phys=" TARGET_FMT_plx
                  ", addr=" TARGET_FMT_plx "\n", val, size, addr, addr);
        }
    } else {
        uint32_t port = addr + dev_region->u.r_baseport;

        if (data) {
            DEBUG("out data=%" PRIx64 ", size=%d, e_phys=" TARGET_FMT_plx
                  ", host=%x\n", *data, size, addr, port);
            switch (size) {
            case 1:
                outb(*data, port);
                break;
            case 2:
                outw(*data, port);
                break;
            case 4:
                outl(*data, port);
                break;
            }
        } else {
            switch (size) {
            case 1:
                val = inb(port);
                break;
            case 2:
                val = inw(port);
                break;
            case 4:
                val = inl(port);
                break;
            }
            DEBUG("in data=%" PRIx64 ", size=%d, e_phys=" TARGET_FMT_plx
                  ", host=%x\n", val, size, addr, port);
        }
    }
    return val;
}

static void assigned_dev_ioport_write(void *opaque, hwaddr addr,
                                      uint64_t data, unsigned size)
{
    assigned_dev_ioport_rw(opaque, addr, size, &data);
}

static uint64_t assigned_dev_ioport_read(void *opaque,
                                         hwaddr addr, unsigned size)
{
    return assigned_dev_ioport_rw(opaque, addr, size, NULL);
}

static uint32_t slow_bar_readb(void *opaque, hwaddr addr)
{
    AssignedDevRegion *d = opaque;
    uint8_t *in = d->u.r_virtbase + addr;
    uint32_t r;

    r = *in;
    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, r);

    return r;
}

static uint32_t slow_bar_readw(void *opaque, hwaddr addr)
{
    AssignedDevRegion *d = opaque;
    uint16_t *in = (uint16_t *)(d->u.r_virtbase + addr);
    uint32_t r;

    r = *in;
    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, r);

    return r;
}

static uint32_t slow_bar_readl(void *opaque, hwaddr addr)
{
    AssignedDevRegion *d = opaque;
    uint32_t *in = (uint32_t *)(d->u.r_virtbase + addr);
    uint32_t r;

    r = *in;
    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, r);

    return r;
}

static void slow_bar_writeb(void *opaque, hwaddr addr, uint32_t val)
{
    AssignedDevRegion *d = opaque;
    uint8_t *out = d->u.r_virtbase + addr;

    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%02x\n", addr, val);
    *out = val;
}

static void slow_bar_writew(void *opaque, hwaddr addr, uint32_t val)
{
    AssignedDevRegion *d = opaque;
    uint16_t *out = (uint16_t *)(d->u.r_virtbase + addr);

    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%04x\n", addr, val);
    *out = val;
}

static void slow_bar_writel(void *opaque, hwaddr addr, uint32_t val)
{
    AssignedDevRegion *d = opaque;
    uint32_t *out = (uint32_t *)(d->u.r_virtbase + addr);

    DEBUG("addr=0x" TARGET_FMT_plx " val=0x%08x\n", addr, val);
    *out = val;
}

static const MemoryRegionOps slow_bar_ops = {
    .old_mmio = {
        .read = { slow_bar_readb, slow_bar_readw, slow_bar_readl, },
        .write = { slow_bar_writeb, slow_bar_writew, slow_bar_writel, },
    },
    .endianness = DEVICE_NATIVE_ENDIAN,
};

static void assigned_dev_iomem_setup(PCIDevice *pci_dev, int region_num,
                                     pcibus_t e_size)
{
    AssignedDevice *r_dev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    AssignedDevRegion *region = &r_dev->v_addrs[region_num];
    PCIRegion *real_region = &r_dev->real_device.regions[region_num];

    if (e_size > 0) {
        memory_region_init(&region->container, OBJECT(pci_dev),
                           "assigned-dev-container", e_size);
        memory_region_add_subregion(&region->container, 0, &region->real_iomem);

        /* deal with MSI-X MMIO page */
        if (real_region->base_addr <= r_dev->msix_table_addr &&
                real_region->base_addr + real_region->size >
                r_dev->msix_table_addr) {
            uint64_t offset = r_dev->msix_table_addr - real_region->base_addr;

            memory_region_add_subregion_overlap(&region->container,
                                                offset,
                                                &r_dev->mmio,
                                                1);
        }
    }
}

static const MemoryRegionOps assigned_dev_ioport_ops = {
    .read = assigned_dev_ioport_read,
    .write = assigned_dev_ioport_write,
    .endianness = DEVICE_NATIVE_ENDIAN,
};

static void assigned_dev_ioport_setup(PCIDevice *pci_dev, int region_num,
                                      pcibus_t size)
{
    AssignedDevice *r_dev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    AssignedDevRegion *region = &r_dev->v_addrs[region_num];

    region->e_size = size;
    memory_region_init(&region->container, OBJECT(pci_dev),
                       "assigned-dev-container", size);
    memory_region_init_io(&region->real_iomem, OBJECT(pci_dev),
                          &assigned_dev_ioport_ops, r_dev->v_addrs + region_num,
                          "assigned-dev-iomem", size);
    memory_region_add_subregion(&region->container, 0, &region->real_iomem);
}

static uint32_t assigned_dev_pci_read(PCIDevice *d, int pos, int len)
{
    AssignedDevice *pci_dev = DO_UPCAST(AssignedDevice, dev, d);
    uint32_t val;
    ssize_t ret;
    int fd = pci_dev->real_device.config_fd;

again:
    ret = pread(fd, &val, len, pos);
    if (ret != len) {
        if ((ret < 0) && (errno == EINTR || errno == EAGAIN)) {
            goto again;
        }

        hw_error("pci read failed, ret = %zd errno = %d\n", ret, errno);
    }

    return val;
}

static uint8_t assigned_dev_pci_read_byte(PCIDevice *d, int pos)
{
    return (uint8_t)assigned_dev_pci_read(d, pos, 1);
}

static void assigned_dev_pci_write(PCIDevice *d, int pos, uint32_t val, int len)
{
    AssignedDevice *pci_dev = DO_UPCAST(AssignedDevice, dev, d);
    ssize_t ret;
    int fd = pci_dev->real_device.config_fd;

again:
    ret = pwrite(fd, &val, len, pos);
    if (ret != len) {
        if ((ret < 0) && (errno == EINTR || errno == EAGAIN)) {
            goto again;
        }

        hw_error("pci write failed, ret = %zd errno = %d\n", ret, errno);
    }
}

static void assigned_dev_emulate_config_read(AssignedDevice *dev,
                                             uint32_t offset, uint32_t len)
{
    memset(dev->emulate_config_read + offset, 0xff, len);
}

static void assigned_dev_direct_config_read(AssignedDevice *dev,
                                            uint32_t offset, uint32_t len)
{
    memset(dev->emulate_config_read + offset, 0, len);
}

static void assigned_dev_direct_config_write(AssignedDevice *dev,
                                             uint32_t offset, uint32_t len)
{
    memset(dev->emulate_config_write + offset, 0, len);
}

static uint8_t pci_find_cap_offset(PCIDevice *d, uint8_t cap, uint8_t start)
{
    int id;
    int max_cap = 48;
    int pos = start ? start : PCI_CAPABILITY_LIST;
    int status;

    status = assigned_dev_pci_read_byte(d, PCI_STATUS);
    if ((status & PCI_STATUS_CAP_LIST) == 0) {
        return 0;
    }

    while (max_cap--) {
        pos = assigned_dev_pci_read_byte(d, pos);
        if (pos < 0x40) {
            break;
        }

        pos &= ~3;
        id = assigned_dev_pci_read_byte(d, pos + PCI_CAP_LIST_ID);

        if (id == 0xff) {
            break;
        }
        if (id == cap) {
            return pos;
        }

        pos += PCI_CAP_LIST_NEXT;
    }
    return 0;
}

static int assigned_dev_register_regions(PCIRegion *io_regions,
                                         unsigned long regions_num,
                                         AssignedDevice *pci_dev)
{
    uint32_t i;
    PCIRegion *cur_region = io_regions;

    for (i = 0; i < regions_num; i++, cur_region++) {
        if (!cur_region->valid) {
            continue;
        }

        /* handle memory io regions */
        if (cur_region->type & IORESOURCE_MEM) {
            int t = PCI_BASE_ADDRESS_SPACE_MEMORY;
            if (cur_region->type & IORESOURCE_PREFETCH) {
                t |= PCI_BASE_ADDRESS_MEM_PREFETCH;
            }
            if (cur_region->type & IORESOURCE_MEM_64) {
                t |= PCI_BASE_ADDRESS_MEM_TYPE_64;
            }

            /* map physical memory */
            pci_dev->v_addrs[i].u.r_virtbase = mmap(NULL, cur_region->size,
                                                    PROT_WRITE | PROT_READ,
                                                    MAP_SHARED,
                                                    cur_region->resource_fd,
                                                    (off_t)0);

            if (pci_dev->v_addrs[i].u.r_virtbase == MAP_FAILED) {
                pci_dev->v_addrs[i].u.r_virtbase = NULL;
                error_report("%s: Error: Couldn't mmap 0x%" PRIx64 "!",
                             __func__, cur_region->base_addr);
                return -1;
            }

            pci_dev->v_addrs[i].r_size = cur_region->size;
            pci_dev->v_addrs[i].e_size = 0;

            /* add offset */
            pci_dev->v_addrs[i].u.r_virtbase +=
                (cur_region->base_addr & 0xFFF);

            if (cur_region->size & 0xFFF) {
                error_report("PCI region %d at address 0x%" PRIx64 " has "
                             "size 0x%" PRIx64 ", which is not a multiple of "
                             "4K.  You might experience some performance hit "
                             "due to that.",
                             i, cur_region->base_addr, cur_region->size);
                memory_region_init_io(&pci_dev->v_addrs[i].real_iomem,
                                      OBJECT(pci_dev), &slow_bar_ops,
                                      &pci_dev->v_addrs[i],
                                      "assigned-dev-slow-bar",
                                      cur_region->size);
            } else {
                void *virtbase = pci_dev->v_addrs[i].u.r_virtbase;
                char name[32];
                snprintf(name, sizeof(name), "%s.bar%d",
                         object_get_typename(OBJECT(pci_dev)), i);
                memory_region_init_ram_ptr(&pci_dev->v_addrs[i].real_iomem,
                                           OBJECT(pci_dev), name,
                                           cur_region->size, virtbase);
                vmstate_register_ram(&pci_dev->v_addrs[i].real_iomem,
                                     &pci_dev->dev.qdev);
            }

            assigned_dev_iomem_setup(&pci_dev->dev, i, cur_region->size);
            pci_register_bar((PCIDevice *) pci_dev, i, t,
                             &pci_dev->v_addrs[i].container);
            continue;
        } else {
            /* handle port io regions */
            uint32_t val;
            int ret;

            /* Test kernel support for ioport resource read/write.  Old
             * kernels return EIO.  New kernels only allow 1/2/4 byte reads
             * so should return EINVAL for a 3 byte read */
            ret = pread(pci_dev->v_addrs[i].region->resource_fd, &val, 3, 0);
            if (ret >= 0) {
                error_report("Unexpected return from I/O port read: %d", ret);
                abort();
            } else if (errno != EINVAL) {
                error_report("Kernel doesn't support ioport resource "
                             "access, hiding this region.");
                close(pci_dev->v_addrs[i].region->resource_fd);
                cur_region->valid = 0;
                continue;
            }

            pci_dev->v_addrs[i].u.r_baseport = cur_region->base_addr;
            pci_dev->v_addrs[i].r_size = cur_region->size;
            pci_dev->v_addrs[i].e_size = 0;

            assigned_dev_ioport_setup(&pci_dev->dev, i, cur_region->size);
            pci_register_bar((PCIDevice *) pci_dev, i,
                             PCI_BASE_ADDRESS_SPACE_IO,
                             &pci_dev->v_addrs[i].container);
        }
    }

    /* success */
    return 0;
}

static int get_real_id(const char *devpath, const char *idname, uint16_t *val)
{
    FILE *f;
    char name[128];
    long id;

    snprintf(name, sizeof(name), "%s%s", devpath, idname);
    f = fopen(name, "r");
    if (f == NULL) {
        error_report("%s: %s: %m", __func__, name);
        return -1;
    }
    if (fscanf(f, "%li\n", &id) == 1) {
        *val = id;
    } else {
        fclose(f);
        return -1;
    }
    fclose(f);

    return 0;
}

static int get_real_vendor_id(const char *devpath, uint16_t *val)
{
    return get_real_id(devpath, "vendor", val);
}

static int get_real_device_id(const char *devpath, uint16_t *val)
{
    return get_real_id(devpath, "device", val);
}

static int get_real_device(AssignedDevice *pci_dev, uint16_t r_seg,
                           uint8_t r_bus, uint8_t r_dev, uint8_t r_func)
{
    char dir[128], name[128];
    int fd, r = 0, v;
    FILE *f;
    uint64_t start, end, size, flags;
    uint16_t id;
    PCIRegion *rp;
    PCIDevRegions *dev = &pci_dev->real_device;

    dev->region_number = 0;

    snprintf(dir, sizeof(dir), "/sys/bus/pci/devices/%04x:%02x:%02x.%x/",
             r_seg, r_bus, r_dev, r_func);

    snprintf(name, sizeof(name), "%sconfig", dir);

    if (pci_dev->configfd_name && *pci_dev->configfd_name) {
        dev->config_fd = monitor_handle_fd_param(cur_mon, pci_dev->configfd_name);
        if (dev->config_fd < 0) {
            return 1;
        }
    } else {
        dev->config_fd = open(name, O_RDWR);

        if (dev->config_fd == -1) {
            error_report("%s: %s: %m", __func__, name);
            return 1;
        }
    }
again:
    r = read(dev->config_fd, pci_dev->dev.config,
             pci_config_size(&pci_dev->dev));
    if (r < 0) {
        if (errno == EINTR || errno == EAGAIN) {
            goto again;
        }
        error_report("%s: read failed, errno = %d", __func__, errno);
    }

    /* Restore or clear multifunction, this is always controlled by qemu */
    if (pci_dev->dev.cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
        pci_dev->dev.config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
    } else {
        pci_dev->dev.config[PCI_HEADER_TYPE] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION;
    }

    /* Clear host resource mapping info.  If we choose not to register a
     * BAR, such as might be the case with the option ROM, we can get
     * confusing, unwritable, residual addresses from the host here. */
    memset(&pci_dev->dev.config[PCI_BASE_ADDRESS_0], 0, 24);
    memset(&pci_dev->dev.config[PCI_ROM_ADDRESS], 0, 4);

    snprintf(name, sizeof(name), "%sresource", dir);

    f = fopen(name, "r");
    if (f == NULL) {
        error_report("%s: %s: %m", __func__, name);
        return 1;
    }

    for (r = 0; r < PCI_ROM_SLOT; r++) {
        if (fscanf(f, "%" SCNi64 " %" SCNi64 " %" SCNi64 "\n",
                   &start, &end, &flags) != 3) {
            break;
        }

        rp = dev->regions + r;
        rp->valid = 0;
        rp->resource_fd = -1;
        size = end - start + 1;
        flags &= IORESOURCE_IO | IORESOURCE_MEM | IORESOURCE_PREFETCH
                 | IORESOURCE_MEM_64;
        if (size == 0 || (flags & ~IORESOURCE_PREFETCH) == 0) {
            continue;
        }
        if (flags & IORESOURCE_MEM) {
            flags &= ~IORESOURCE_IO;
        } else {
            flags &= ~IORESOURCE_PREFETCH;
        }
        snprintf(name, sizeof(name), "%sresource%d", dir, r);
        fd = open(name, O_RDWR);
        if (fd == -1) {
            continue;
        }
        rp->resource_fd = fd;

        rp->type = flags;
        rp->valid = 1;
        rp->base_addr = start;
        rp->size = size;
        pci_dev->v_addrs[r].region = rp;
        DEBUG("region %d size %" PRIu64 " start 0x%" PRIx64
              " type %d resource_fd %d\n",
              r, rp->size, start, rp->type, rp->resource_fd);
    }

    fclose(f);

    /* read and fill vendor ID */
    v = get_real_vendor_id(dir, &id);
    if (v) {
        return 1;
    }
    pci_dev->dev.config[0] = id & 0xff;
    pci_dev->dev.config[1] = (id & 0xff00) >> 8;

    /* read and fill device ID */
    v = get_real_device_id(dir, &id);
    if (v) {
        return 1;
    }
    pci_dev->dev.config[2] = id & 0xff;
    pci_dev->dev.config[3] = (id & 0xff00) >> 8;

    pci_word_test_and_clear_mask(pci_dev->emulate_config_write + PCI_COMMAND,
                                 PCI_COMMAND_MASTER | PCI_COMMAND_INTX_DISABLE);

    dev->region_number = r;
    return 0;
}

static void free_msi_virqs(AssignedDevice *dev)
{
    int i;

    for (i = 0; i < dev->msi_virq_nr; i++) {
        if (dev->msi_virq[i] >= 0) {
            kvm_irqchip_release_virq(kvm_state, dev->msi_virq[i]);
            dev->msi_virq[i] = -1;
        }
    }
    g_free(dev->msi_virq);
    dev->msi_virq = NULL;
    dev->msi_virq_nr = 0;
}

static void free_assigned_device(AssignedDevice *dev)
{
    int i;

    if (dev->cap.available & ASSIGNED_DEVICE_CAP_MSIX) {
        assigned_dev_unregister_msix_mmio(dev);
    }
    for (i = 0; i < dev->real_device.region_number; i++) {
        PCIRegion *pci_region = &dev->real_device.regions[i];
        AssignedDevRegion *region = &dev->v_addrs[i];

        if (!pci_region->valid) {
            continue;
        }
        if (pci_region->type & IORESOURCE_IO) {
            if (region->u.r_baseport) {
                memory_region_del_subregion(&region->container,
                                            &region->real_iomem);
                memory_region_destroy(&region->real_iomem);
                memory_region_destroy(&region->container);
            }
        } else if (pci_region->type & IORESOURCE_MEM) {
            if (region->u.r_virtbase) {
                memory_region_del_subregion(&region->container,
                                            &region->real_iomem);

                /* Remove MSI-X table subregion */
                if (pci_region->base_addr <= dev->msix_table_addr &&
                    pci_region->base_addr + pci_region->size >
                    dev->msix_table_addr) {
                    memory_region_del_subregion(&region->container,
                                                &dev->mmio);
                }

                memory_region_destroy(&region->real_iomem);
                memory_region_destroy(&region->container);
                if (munmap(region->u.r_virtbase,
                           (pci_region->size + 0xFFF) & 0xFFFFF000)) {
                    error_report("Failed to unmap assigned device region: %s",
                                 strerror(errno));
                }
            }
        }
        if (pci_region->resource_fd >= 0) {
            close(pci_region->resource_fd);
        }
    }

    if (dev->real_device.config_fd >= 0) {
        close(dev->real_device.config_fd);
    }

    free_msi_virqs(dev);
}

static void assign_failed_examine(AssignedDevice *dev)
{
    char name[PATH_MAX], dir[PATH_MAX], driver[PATH_MAX] = {}, *ns;
    uint16_t vendor_id, device_id;
    int r;

    snprintf(dir, sizeof(dir), "/sys/bus/pci/devices/%04x:%02x:%02x.%01x/",
            dev->host.domain, dev->host.bus, dev->host.slot,
            dev->host.function);

    snprintf(name, sizeof(name), "%sdriver", dir);

    r = readlink(name, driver, sizeof(driver));
    if ((r <= 0) || r >= sizeof(driver)) {
        goto fail;
    }

    ns = strrchr(driver, '/');
    if (!ns) {
        goto fail;
    }

    ns++;

    if (get_real_vendor_id(dir, &vendor_id) ||
        get_real_device_id(dir, &device_id)) {
        goto fail;
    }

    error_report("*** The driver '%s' is occupying your device "
                 "%04x:%02x:%02x.%x.",
                 ns, dev->host.domain, dev->host.bus, dev->host.slot,
                 dev->host.function);
    error_report("***");
    error_report("*** You can try the following commands to free it:");
    error_report("***");
    error_report("*** $ echo \"%04x %04x\" > /sys/bus/pci/drivers/pci-stub/"
                 "new_id", vendor_id, device_id);
    error_report("*** $ echo \"%04x:%02x:%02x.%x\" > /sys/bus/pci/drivers/"
                 "%s/unbind",
                 dev->host.domain, dev->host.bus, dev->host.slot,
                 dev->host.function, ns);
    error_report("*** $ echo \"%04x:%02x:%02x.%x\" > /sys/bus/pci/drivers/"
                 "pci-stub/bind",
                 dev->host.domain, dev->host.bus, dev->host.slot,
                 dev->host.function);
    error_report("*** $ echo \"%04x %04x\" > /sys/bus/pci/drivers/pci-stub"
                 "/remove_id", vendor_id, device_id);
    error_report("***");

    return;

fail:
    error_report("Couldn't find out why.");
}

static int assign_device(AssignedDevice *dev)
{
    uint32_t flags = KVM_DEV_ASSIGN_ENABLE_IOMMU;
    int r;

    /* Only pass non-zero PCI segment to capable module */
    if (!kvm_check_extension(kvm_state, KVM_CAP_PCI_SEGMENT) &&
        dev->host.domain) {
        error_report("Can't assign device inside non-zero PCI segment "
                     "as this KVM module doesn't support it.");
        return -ENODEV;
    }

    if (!kvm_check_extension(kvm_state, KVM_CAP_IOMMU)) {
        error_report("No IOMMU found.  Unable to assign device \"%s\"",
                     dev->dev.qdev.id);
        return -ENODEV;
    }

    if (dev->features & ASSIGNED_DEVICE_SHARE_INTX_MASK &&
        kvm_has_intx_set_mask()) {
        flags |= KVM_DEV_ASSIGN_PCI_2_3;
    }

    r = kvm_device_pci_assign(kvm_state, &dev->host, flags, &dev->dev_id);
    if (r < 0) {
        error_report("Failed to assign device \"%s\" : %s",
                     dev->dev.qdev.id, strerror(-r));

        switch (r) {
        case -EBUSY:
            assign_failed_examine(dev);
            break;
        default:
            break;
        }
    }
    return r;
}

static bool check_irqchip_in_kernel(void)
{
    if (kvm_irqchip_in_kernel()) {
        return true;
    }
    error_report("pci-assign: error: requires KVM with in-kernel irqchip "
                 "enabled");
    return false;
}

static int assign_intx(AssignedDevice *dev)
{
    AssignedIRQType new_type;
    PCIINTxRoute intx_route;
    bool intx_host_msi;
    int r;

    /* Interrupt PIN 0 means don't use INTx */
    if (assigned_dev_pci_read_byte(&dev->dev, PCI_INTERRUPT_PIN) == 0) {
        pci_device_set_intx_routing_notifier(&dev->dev, NULL);
        return 0;
    }

    if (!check_irqchip_in_kernel()) {
        return -ENOTSUP;
    }

    pci_device_set_intx_routing_notifier(&dev->dev,
                                         assigned_dev_update_irq_routing);

    intx_route = pci_device_route_intx_to_irq(&dev->dev, dev->intpin);
    assert(intx_route.mode != PCI_INTX_INVERTED);

    if (!pci_intx_route_changed(&dev->intx_route, &intx_route)) {
        return 0;
    }

    switch (dev->assigned_irq_type) {
    case ASSIGNED_IRQ_INTX_HOST_INTX:
    case ASSIGNED_IRQ_INTX_HOST_MSI:
        intx_host_msi = dev->assigned_irq_type == ASSIGNED_IRQ_INTX_HOST_MSI;
        r = kvm_device_intx_deassign(kvm_state, dev->dev_id, intx_host_msi);
        break;
    case ASSIGNED_IRQ_MSI:
        r = kvm_device_msi_deassign(kvm_state, dev->dev_id);
        break;
    case ASSIGNED_IRQ_MSIX:
        r = kvm_device_msix_deassign(kvm_state, dev->dev_id);
        break;
    default:
        r = 0;
        break;
    }
    if (r) {
        perror("assign_intx: deassignment of previous interrupt failed");
    }
    dev->assigned_irq_type = ASSIGNED_IRQ_NONE;

    if (intx_route.mode == PCI_INTX_DISABLED) {
        dev->intx_route = intx_route;
        return 0;
    }

retry:
    if (dev->features & ASSIGNED_DEVICE_PREFER_MSI_MASK &&
        dev->cap.available & ASSIGNED_DEVICE_CAP_MSI) {
        intx_host_msi = true;
        new_type = ASSIGNED_IRQ_INTX_HOST_MSI;
    } else {
        intx_host_msi = false;
        new_type = ASSIGNED_IRQ_INTX_HOST_INTX;
    }

    r = kvm_device_intx_assign(kvm_state, dev->dev_id, intx_host_msi,
                               intx_route.irq);
    if (r < 0) {
        if (r == -EIO && !(dev->features & ASSIGNED_DEVICE_PREFER_MSI_MASK) &&
            dev->cap.available & ASSIGNED_DEVICE_CAP_MSI) {
            /* Retry with host-side MSI. There might be an IRQ conflict and
             * either the kernel or the device doesn't support sharing. */
            error_report("Host-side INTx sharing not supported, "
                         "using MSI instead");
            error_printf("Some devices do not work properly in this mode.\n");
            dev->features |= ASSIGNED_DEVICE_PREFER_MSI_MASK;
            goto retry;
        }
        error_report("Failed to assign irq for \"%s\": %s",
                     dev->dev.qdev.id, strerror(-r));
        error_report("Perhaps you are assigning a device "
                     "that shares an IRQ with another device?");
        return r;
    }

    dev->intx_route = intx_route;
    dev->assigned_irq_type = new_type;
    return r;
}

static void deassign_device(AssignedDevice *dev)
{
    int r;

    r = kvm_device_pci_deassign(kvm_state, dev->dev_id);
    assert(r == 0);
}

/* The pci config space got updated. Check if irq numbers have changed
 * for our devices
 */
static void assigned_dev_update_irq_routing(PCIDevice *dev)
{
    AssignedDevice *assigned_dev = DO_UPCAST(AssignedDevice, dev, dev);
    Error *err = NULL;
    int r;

    r = assign_intx(assigned_dev);
    if (r < 0) {
        qdev_unplug(&dev->qdev, &err);
        assert(!err);
    }
}

static void assigned_dev_update_msi(PCIDevice *pci_dev)
{
    AssignedDevice *assigned_dev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    uint8_t ctrl_byte = pci_get_byte(pci_dev->config + pci_dev->msi_cap +
                                     PCI_MSI_FLAGS);
    int r;

    /* Some guests gratuitously disable MSI even if they're not using it,
     * try to catch this by only deassigning irqs if the guest is using
     * MSI or intends to start. */
    if (assigned_dev->assigned_irq_type == ASSIGNED_IRQ_MSI ||
        (ctrl_byte & PCI_MSI_FLAGS_ENABLE)) {
        r = kvm_device_msi_deassign(kvm_state, assigned_dev->dev_id);
        /* -ENXIO means no assigned irq */
        if (r && r != -ENXIO) {
            perror("assigned_dev_update_msi: deassign irq");
        }

        free_msi_virqs(assigned_dev);

        assigned_dev->assigned_irq_type = ASSIGNED_IRQ_NONE;
        pci_device_set_intx_routing_notifier(pci_dev, NULL);
    }

    if (ctrl_byte & PCI_MSI_FLAGS_ENABLE) {
        MSIMessage msg = msi_get_message(pci_dev, 0);
        int virq;

        virq = kvm_irqchip_add_msi_route(kvm_state, msg);
        if (virq < 0) {
            perror("assigned_dev_update_msi: kvm_irqchip_add_msi_route");
            return;
        }

        assigned_dev->msi_virq = g_malloc(sizeof(*assigned_dev->msi_virq));
        assigned_dev->msi_virq_nr = 1;
        assigned_dev->msi_virq[0] = virq;
        if (kvm_device_msi_assign(kvm_state, assigned_dev->dev_id, virq) < 0) {
            perror("assigned_dev_update_msi: kvm_device_msi_assign");
        }

        assigned_dev->intx_route.mode = PCI_INTX_DISABLED;
        assigned_dev->intx_route.irq = -1;
        assigned_dev->assigned_irq_type = ASSIGNED_IRQ_MSI;
    } else {
        assign_intx(assigned_dev);
    }
}

static void assigned_dev_update_msi_msg(PCIDevice *pci_dev)
{
    AssignedDevice *assigned_dev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    uint8_t ctrl_byte = pci_get_byte(pci_dev->config + pci_dev->msi_cap +
                                     PCI_MSI_FLAGS);

    if (assigned_dev->assigned_irq_type != ASSIGNED_IRQ_MSI ||
        !(ctrl_byte & PCI_MSI_FLAGS_ENABLE)) {
        return;
    }

    kvm_irqchip_update_msi_route(kvm_state, assigned_dev->msi_virq[0],
                                 msi_get_message(pci_dev, 0));
}

static bool assigned_dev_msix_masked(MSIXTableEntry *entry)
{
    return (entry->ctrl & cpu_to_le32(0x1)) != 0;
}

/*
 * When MSI-X is first enabled the vector table typically has all the
 * vectors masked, so we can't use that as the obvious test to figure out
 * how many vectors to initially enable.  Instead we look at the data field
 * because this is what worked for pci-assign for a long time.  This makes
 * sure the physical MSI-X state tracks the guest's view, which is important
 * for some VF/PF and PF/fw communication channels.
 */
static bool assigned_dev_msix_skipped(MSIXTableEntry *entry)
{
    return !entry->data;
}

static int assigned_dev_update_msix_mmio(PCIDevice *pci_dev)
{
    AssignedDevice *adev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    uint16_t entries_nr = 0;
    int i, r = 0;
    MSIXTableEntry *entry = adev->msix_table;
    MSIMessage msg;

    /* Get the usable entry number for allocating */
    for (i = 0; i < adev->msix_max; i++, entry++) {
        if (assigned_dev_msix_skipped(entry)) {
            continue;
        }
        entries_nr++;
    }

    DEBUG("MSI-X entries: %d\n", entries_nr);

    /* It's valid to enable MSI-X with all entries masked */
    if (!entries_nr) {
        return 0;
    }

    r = kvm_device_msix_init_vectors(kvm_state, adev->dev_id, entries_nr);
    if (r != 0) {
        error_report("fail to set MSI-X entry number for MSIX! %s",
                     strerror(-r));
        return r;
    }

    free_msi_virqs(adev);

    adev->msi_virq_nr = adev->msix_max;
    adev->msi_virq = g_malloc(adev->msix_max * sizeof(*adev->msi_virq));

    entry = adev->msix_table;
    for (i = 0; i < adev->msix_max; i++, entry++) {
        adev->msi_virq[i] = -1;

        if (assigned_dev_msix_skipped(entry)) {
            continue;
        }

        msg.address = entry->addr_lo | ((uint64_t)entry->addr_hi << 32);
        msg.data = entry->data;
        r = kvm_irqchip_add_msi_route(kvm_state, msg);
        if (r < 0) {
            return r;
        }
        adev->msi_virq[i] = r;

        DEBUG("MSI-X vector %d, gsi %d, addr %08x_%08x, data %08x\n", i,
              r, entry->addr_hi, entry->addr_lo, entry->data);

        r = kvm_device_msix_set_vector(kvm_state, adev->dev_id, i,
                                       adev->msi_virq[i]);
        if (r) {
            error_report("fail to set MSI-X entry! %s", strerror(-r));
            break;
        }
    }

    return r;
}

static void assigned_dev_update_msix(PCIDevice *pci_dev)
{
    AssignedDevice *assigned_dev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    uint16_t ctrl_word = pci_get_word(pci_dev->config + pci_dev->msix_cap +
                                      PCI_MSIX_FLAGS);
    int r;

    /* Some guests gratuitously disable MSIX even if they're not using it,
     * try to catch this by only deassigning irqs if the guest is using
     * MSIX or intends to start. */
    if ((assigned_dev->assigned_irq_type == ASSIGNED_IRQ_MSIX) ||
        (ctrl_word & PCI_MSIX_FLAGS_ENABLE)) {
        r = kvm_device_msix_deassign(kvm_state, assigned_dev->dev_id);
        /* -ENXIO means no assigned irq */
        if (r && r != -ENXIO) {
            perror("assigned_dev_update_msix: deassign irq");
        }

        free_msi_virqs(assigned_dev);

        assigned_dev->assigned_irq_type = ASSIGNED_IRQ_NONE;
        pci_device_set_intx_routing_notifier(pci_dev, NULL);
    }

    if (ctrl_word & PCI_MSIX_FLAGS_ENABLE) {
        if (assigned_dev_update_msix_mmio(pci_dev) < 0) {
            perror("assigned_dev_update_msix_mmio");
            return;
        }

        if (assigned_dev->msi_virq_nr > 0) {
            if (kvm_device_msix_assign(kvm_state, assigned_dev->dev_id) < 0) {
                perror("assigned_dev_enable_msix: assign irq");
                return;
            }
        }
        assigned_dev->intx_route.mode = PCI_INTX_DISABLED;
        assigned_dev->intx_route.irq = -1;
        assigned_dev->assigned_irq_type = ASSIGNED_IRQ_MSIX;
    } else {
        assign_intx(assigned_dev);
    }
}

static uint32_t assigned_dev_pci_read_config(PCIDevice *pci_dev,
                                             uint32_t address, int len)
{
    AssignedDevice *assigned_dev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    uint32_t virt_val = pci_default_read_config(pci_dev, address, len);
    uint32_t real_val, emulate_mask, full_emulation_mask;

    emulate_mask = 0;
    memcpy(&emulate_mask, assigned_dev->emulate_config_read + address, len);
    emulate_mask = le32_to_cpu(emulate_mask);

    full_emulation_mask = 0xffffffff >> (32 - len * 8);

    if (emulate_mask != full_emulation_mask) {
        real_val = assigned_dev_pci_read(pci_dev, address, len);
        return (virt_val & emulate_mask) | (real_val & ~emulate_mask);
    } else {
        return virt_val;
    }
}

static void assigned_dev_pci_write_config(PCIDevice *pci_dev, uint32_t address,
                                          uint32_t val, int len)
{
    AssignedDevice *assigned_dev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    uint16_t old_cmd = pci_get_word(pci_dev->config + PCI_COMMAND);
    uint32_t emulate_mask, full_emulation_mask;
    int ret;

    pci_default_write_config(pci_dev, address, val, len);

    if (kvm_has_intx_set_mask() &&
        range_covers_byte(address, len, PCI_COMMAND + 1)) {
        bool intx_masked = (pci_get_word(pci_dev->config + PCI_COMMAND) &
                            PCI_COMMAND_INTX_DISABLE);

        if (intx_masked != !!(old_cmd & PCI_COMMAND_INTX_DISABLE)) {
            ret = kvm_device_intx_set_mask(kvm_state, assigned_dev->dev_id,
                                           intx_masked);
            if (ret) {
                perror("assigned_dev_pci_write_config: set intx mask");
            }
        }
    }
    if (assigned_dev->cap.available & ASSIGNED_DEVICE_CAP_MSI) {
        if (range_covers_byte(address, len,
                              pci_dev->msi_cap + PCI_MSI_FLAGS)) {
            assigned_dev_update_msi(pci_dev);
        } else if (ranges_overlap(address, len, /* 32bit MSI only */
                                  pci_dev->msi_cap + PCI_MSI_ADDRESS_LO, 6)) {
            assigned_dev_update_msi_msg(pci_dev);
        }
    }
    if (assigned_dev->cap.available & ASSIGNED_DEVICE_CAP_MSIX) {
        if (range_covers_byte(address, len,
                              pci_dev->msix_cap + PCI_MSIX_FLAGS + 1)) {
            assigned_dev_update_msix(pci_dev);
        }
    }

    emulate_mask = 0;
    memcpy(&emulate_mask, assigned_dev->emulate_config_write + address, len);
    emulate_mask = le32_to_cpu(emulate_mask);

    full_emulation_mask = 0xffffffff >> (32 - len * 8);

    if (emulate_mask != full_emulation_mask) {
        if (emulate_mask) {
            val &= ~emulate_mask;
            val |= assigned_dev_pci_read(pci_dev, address, len) & emulate_mask;
        }
        assigned_dev_pci_write(pci_dev, address, val, len);
    }
}

static void assigned_dev_setup_cap_read(AssignedDevice *dev, uint32_t offset,
                                        uint32_t len)
{
    assigned_dev_direct_config_read(dev, offset, len);
    assigned_dev_emulate_config_read(dev, offset + PCI_CAP_LIST_NEXT, 1);
}

static int assigned_device_pci_cap_init(PCIDevice *pci_dev)
{
    AssignedDevice *dev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    PCIRegion *pci_region = dev->real_device.regions;
    int ret, pos;

    /* Clear initial capabilities pointer and status copied from hw */
    pci_set_byte(pci_dev->config + PCI_CAPABILITY_LIST, 0);
    pci_set_word(pci_dev->config + PCI_STATUS,
                 pci_get_word(pci_dev->config + PCI_STATUS) &
                 ~PCI_STATUS_CAP_LIST);

    /* Expose MSI capability
     * MSI capability is the 1st capability in capability config */
    pos = pci_find_cap_offset(pci_dev, PCI_CAP_ID_MSI, 0);
    if (pos != 0 && kvm_check_extension(kvm_state, KVM_CAP_ASSIGN_DEV_IRQ)) {
        if (!check_irqchip_in_kernel()) {
            return -ENOTSUP;
        }
        dev->cap.available |= ASSIGNED_DEVICE_CAP_MSI;
        /* Only 32-bit/no-mask currently supported */
        ret = pci_add_capability(pci_dev, PCI_CAP_ID_MSI, pos, 10);
        if (ret < 0) {
            return ret;
        }
        pci_dev->msi_cap = pos;

        pci_set_word(pci_dev->config + pos + PCI_MSI_FLAGS,
                     pci_get_word(pci_dev->config + pos + PCI_MSI_FLAGS) &
                     PCI_MSI_FLAGS_QMASK);
        pci_set_long(pci_dev->config + pos + PCI_MSI_ADDRESS_LO, 0);
        pci_set_word(pci_dev->config + pos + PCI_MSI_DATA_32, 0);

        /* Set writable fields */
        pci_set_word(pci_dev->wmask + pos + PCI_MSI_FLAGS,
                     PCI_MSI_FLAGS_QSIZE | PCI_MSI_FLAGS_ENABLE);
        pci_set_long(pci_dev->wmask + pos + PCI_MSI_ADDRESS_LO, 0xfffffffc);
        pci_set_word(pci_dev->wmask + pos + PCI_MSI_DATA_32, 0xffff);
    }
    /* Expose MSI-X capability */
    pos = pci_find_cap_offset(pci_dev, PCI_CAP_ID_MSIX, 0);
    if (pos != 0 && kvm_device_msix_supported(kvm_state)) {
        int bar_nr;
        uint32_t msix_table_entry;

        if (!check_irqchip_in_kernel()) {
            return -ENOTSUP;
        }
        dev->cap.available |= ASSIGNED_DEVICE_CAP_MSIX;
        ret = pci_add_capability(pci_dev, PCI_CAP_ID_MSIX, pos, 12);
        if (ret < 0) {
            return ret;
        }
        pci_dev->msix_cap = pos;

        pci_set_word(pci_dev->config + pos + PCI_MSIX_FLAGS,
                     pci_get_word(pci_dev->config + pos + PCI_MSIX_FLAGS) &
                     PCI_MSIX_FLAGS_QSIZE);

        /* Only enable and function mask bits are writable */
        pci_set_word(pci_dev->wmask + pos + PCI_MSIX_FLAGS,
                     PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL);

        msix_table_entry = pci_get_long(pci_dev->config + pos + PCI_MSIX_TABLE);
        bar_nr = msix_table_entry & PCI_MSIX_FLAGS_BIRMASK;
        msix_table_entry &= ~PCI_MSIX_FLAGS_BIRMASK;
        dev->msix_table_addr = pci_region[bar_nr].base_addr + msix_table_entry;
        dev->msix_max = pci_get_word(pci_dev->config + pos + PCI_MSIX_FLAGS);
        dev->msix_max &= PCI_MSIX_FLAGS_QSIZE;
        dev->msix_max += 1;
    }

    /* Minimal PM support, nothing writable, device appears to NAK changes */
    pos = pci_find_cap_offset(pci_dev, PCI_CAP_ID_PM, 0);
    if (pos) {
        uint16_t pmc;

        ret = pci_add_capability(pci_dev, PCI_CAP_ID_PM, pos, PCI_PM_SIZEOF);
        if (ret < 0) {
            return ret;
        }

        assigned_dev_setup_cap_read(dev, pos, PCI_PM_SIZEOF);

        pmc = pci_get_word(pci_dev->config + pos + PCI_CAP_FLAGS);
        pmc &= (PCI_PM_CAP_VER_MASK | PCI_PM_CAP_DSI);
        pci_set_word(pci_dev->config + pos + PCI_CAP_FLAGS, pmc);

        /* assign_device will bring the device up to D0, so we don't need
         * to worry about doing that ourselves here. */
        pci_set_word(pci_dev->config + pos + PCI_PM_CTRL,
                     PCI_PM_CTRL_NO_SOFT_RESET);

        pci_set_byte(pci_dev->config + pos + PCI_PM_PPB_EXTENSIONS, 0);
        pci_set_byte(pci_dev->config + pos + PCI_PM_DATA_REGISTER, 0);
    }

    pos = pci_find_cap_offset(pci_dev, PCI_CAP_ID_EXP, 0);
    if (pos) {
        uint8_t version, size = 0;
        uint16_t type, devctl, lnksta;
        uint32_t devcap, lnkcap;

        version = pci_get_byte(pci_dev->config + pos + PCI_EXP_FLAGS);
        version &= PCI_EXP_FLAGS_VERS;
        if (version == 1) {
            size = 0x14;
        } else if (version == 2) {
            /*
             * Check for non-std size, accept reduced size to 0x34,
             * which is what bcm5761 implemented, violating the
             * PCIe v3.0 spec that regs should exist and be read as 0,
             * not optionally provided and shorten the struct size.
             */
            size = MIN(0x3c, PCI_CONFIG_SPACE_SIZE - pos);
            if (size < 0x34) {
                error_report("%s: Invalid size PCIe cap-id 0x%x",
                             __func__, PCI_CAP_ID_EXP);
                return -EINVAL;
            } else if (size != 0x3c) {
                error_report("WARNING, %s: PCIe cap-id 0x%x has "
                             "non-standard size 0x%x; std size should be 0x3c",
                             __func__, PCI_CAP_ID_EXP, size);
            }
        } else if (version == 0) {
            uint16_t vid, did;
            vid = pci_get_word(pci_dev->config + PCI_VENDOR_ID);
            did = pci_get_word(pci_dev->config + PCI_DEVICE_ID);
            if (vid == PCI_VENDOR_ID_INTEL && did == 0x10ed) {
                /*
                 * quirk for Intel 82599 VF with invalid PCIe capability
                 * version, should really be version 2 (same as PF)
                 */
                size = 0x3c;
            }
        }

        if (size == 0) {
            error_report("%s: Unsupported PCI express capability version %d",
                         __func__, version);
            return -EINVAL;
        }

        ret = pci_add_capability(pci_dev, PCI_CAP_ID_EXP, pos, size);
        if (ret < 0) {
            return ret;
        }

        assigned_dev_setup_cap_read(dev, pos, size);

        type = pci_get_word(pci_dev->config + pos + PCI_EXP_FLAGS);
        type = (type & PCI_EXP_FLAGS_TYPE) >> 4;
        if (type != PCI_EXP_TYPE_ENDPOINT &&
            type != PCI_EXP_TYPE_LEG_END && type != PCI_EXP_TYPE_RC_END) {
            error_report("Device assignment only supports endpoint assignment,"
                         " device type %d", type);
            return -EINVAL;
        }

        /* capabilities, pass existing read-only copy
         * PCI_EXP_FLAGS_IRQ: updated by hardware, should be direct read */

        /* device capabilities: hide FLR */
        devcap = pci_get_long(pci_dev->config + pos + PCI_EXP_DEVCAP);
        devcap &= ~PCI_EXP_DEVCAP_FLR;
        pci_set_long(pci_dev->config + pos + PCI_EXP_DEVCAP, devcap);

        /* device control: clear all error reporting enable bits, leaving
         *                 only a few host values.  Note, these are
         *                 all writable, but not passed to hw.
         */
        devctl = pci_get_word(pci_dev->config + pos + PCI_EXP_DEVCTL);
        devctl = (devctl & (PCI_EXP_DEVCTL_READRQ | PCI_EXP_DEVCTL_PAYLOAD)) |
                  PCI_EXP_DEVCTL_RELAX_EN | PCI_EXP_DEVCTL_NOSNOOP_EN;
        pci_set_word(pci_dev->config + pos + PCI_EXP_DEVCTL, devctl);
        devctl = PCI_EXP_DEVCTL_BCR_FLR | PCI_EXP_DEVCTL_AUX_PME;
        pci_set_word(pci_dev->wmask + pos + PCI_EXP_DEVCTL, ~devctl);

        /* Clear device status */
        pci_set_word(pci_dev->config + pos + PCI_EXP_DEVSTA, 0);

        /* Link capabilities, expose links and latencues, clear reporting */
        lnkcap = pci_get_long(pci_dev->config + pos + PCI_EXP_LNKCAP);
        lnkcap &= (PCI_EXP_LNKCAP_SLS | PCI_EXP_LNKCAP_MLW |
                   PCI_EXP_LNKCAP_ASPMS | PCI_EXP_LNKCAP_L0SEL |
                   PCI_EXP_LNKCAP_L1EL);
        pci_set_long(pci_dev->config + pos + PCI_EXP_LNKCAP, lnkcap);

        /* Link control, pass existing read-only copy.  Should be writable? */

        /* Link status, only expose current speed and width */
        lnksta = pci_get_word(pci_dev->config + pos + PCI_EXP_LNKSTA);
        lnksta &= (PCI_EXP_LNKSTA_CLS | PCI_EXP_LNKSTA_NLW);
        pci_set_word(pci_dev->config + pos + PCI_EXP_LNKSTA, lnksta);

        if (version >= 2) {
            /* Slot capabilities, control, status - not needed for endpoints */
            pci_set_long(pci_dev->config + pos + PCI_EXP_SLTCAP, 0);
            pci_set_word(pci_dev->config + pos + PCI_EXP_SLTCTL, 0);
            pci_set_word(pci_dev->config + pos + PCI_EXP_SLTSTA, 0);

            /* Root control, capabilities, status - not needed for endpoints */
            pci_set_word(pci_dev->config + pos + PCI_EXP_RTCTL, 0);
            pci_set_word(pci_dev->config + pos + PCI_EXP_RTCAP, 0);
            pci_set_long(pci_dev->config + pos + PCI_EXP_RTSTA, 0);

            /* Device capabilities/control 2, pass existing read-only copy */
            /* Link control 2, pass existing read-only copy */
        }
    }

    pos = pci_find_cap_offset(pci_dev, PCI_CAP_ID_PCIX, 0);
    if (pos) {
        uint16_t cmd;
        uint32_t status;

        /* Only expose the minimum, 8 byte capability */
        ret = pci_add_capability(pci_dev, PCI_CAP_ID_PCIX, pos, 8);
        if (ret < 0) {
            return ret;
        }

        assigned_dev_setup_cap_read(dev, pos, 8);

        /* Command register, clear upper bits, including extended modes */
        cmd = pci_get_word(pci_dev->config + pos + PCI_X_CMD);
        cmd &= (PCI_X_CMD_DPERR_E | PCI_X_CMD_ERO | PCI_X_CMD_MAX_READ |
                PCI_X_CMD_MAX_SPLIT);
        pci_set_word(pci_dev->config + pos + PCI_X_CMD, cmd);

        /* Status register, update with emulated PCI bus location, clear
         * error bits, leave the rest. */
        status = pci_get_long(pci_dev->config + pos + PCI_X_STATUS);
        status &= ~(PCI_X_STATUS_BUS | PCI_X_STATUS_DEVFN);
        status |= (pci_bus_num(pci_dev->bus) << 8) | pci_dev->devfn;
        status &= ~(PCI_X_STATUS_SPL_DISC | PCI_X_STATUS_UNX_SPL |
                    PCI_X_STATUS_SPL_ERR);
        pci_set_long(pci_dev->config + pos + PCI_X_STATUS, status);
    }

    pos = pci_find_cap_offset(pci_dev, PCI_CAP_ID_VPD, 0);
    if (pos) {
        /* Direct R/W passthrough */
        ret = pci_add_capability(pci_dev, PCI_CAP_ID_VPD, pos, 8);
        if (ret < 0) {
            return ret;
        }

        assigned_dev_setup_cap_read(dev, pos, 8);

        /* direct write for cap content */
        assigned_dev_direct_config_write(dev, pos + 2, 6);
    }

    /* Devices can have multiple vendor capabilities, get them all */
    for (pos = 0; (pos = pci_find_cap_offset(pci_dev, PCI_CAP_ID_VNDR, pos));
        pos += PCI_CAP_LIST_NEXT) {
        uint8_t len = pci_get_byte(pci_dev->config + pos + PCI_CAP_FLAGS);
        /* Direct R/W passthrough */
        ret = pci_add_capability(pci_dev, PCI_CAP_ID_VNDR, pos, len);
        if (ret < 0) {
            return ret;
        }

        assigned_dev_setup_cap_read(dev, pos, len);

        /* direct write for cap content */
        assigned_dev_direct_config_write(dev, pos + 2, len - 2);
    }

    /* If real and virtual capability list status bits differ, virtualize the
     * access. */
    if ((pci_get_word(pci_dev->config + PCI_STATUS) & PCI_STATUS_CAP_LIST) !=
        (assigned_dev_pci_read_byte(pci_dev, PCI_STATUS) &
         PCI_STATUS_CAP_LIST)) {
        dev->emulate_config_read[PCI_STATUS] |= PCI_STATUS_CAP_LIST;
    }

    return 0;
}

static uint64_t
assigned_dev_msix_mmio_read(void *opaque, hwaddr addr,
                            unsigned size)
{
    AssignedDevice *adev = opaque;
    uint64_t val;

    memcpy(&val, (void *)((uint8_t *)adev->msix_table + addr), size);

    return val;
}

static void assigned_dev_msix_mmio_write(void *opaque, hwaddr addr,
                                         uint64_t val, unsigned size)
{
    AssignedDevice *adev = opaque;
    PCIDevice *pdev = &adev->dev;
    uint16_t ctrl;
    MSIXTableEntry orig;
    int i = addr >> 4;

    if (i >= adev->msix_max) {
        return; /* Drop write */
    }

    ctrl = pci_get_word(pdev->config + pdev->msix_cap + PCI_MSIX_FLAGS);

    DEBUG("write to MSI-X table offset 0x%lx, val 0x%lx\n", addr, val);

    if (ctrl & PCI_MSIX_FLAGS_ENABLE) {
        orig = adev->msix_table[i];
    }

    memcpy((uint8_t *)adev->msix_table + addr, &val, size);

    if (ctrl & PCI_MSIX_FLAGS_ENABLE) {
        MSIXTableEntry *entry = &adev->msix_table[i];

        if (!assigned_dev_msix_masked(&orig) &&
            assigned_dev_msix_masked(entry)) {
            /*
             * Vector masked, disable it
             *
             * XXX It's not clear if we can or should actually attempt
             * to mask or disable the interrupt.  KVM doesn't have
             * support for pending bits and kvm_assign_set_msix_entry
             * doesn't modify the device hardware mask.  Interrupts
             * while masked are simply not injected to the guest, so
             * are lost.  Can we get away with always injecting an
             * interrupt on unmask?
             */
        } else if (assigned_dev_msix_masked(&orig) &&
                   !assigned_dev_msix_masked(entry)) {
            /* Vector unmasked */
            if (i >= adev->msi_virq_nr || adev->msi_virq[i] < 0) {
                /* Previously unassigned vector, start from scratch */
                assigned_dev_update_msix(pdev);
                return;
            } else {
                /* Update an existing, previously masked vector */
                MSIMessage msg;
                int ret;

                msg.address = entry->addr_lo |
                    ((uint64_t)entry->addr_hi << 32);
                msg.data = entry->data;

                ret = kvm_irqchip_update_msi_route(kvm_state,
                                                   adev->msi_virq[i], msg);
                if (ret) {
                    error_report("Error updating irq routing entry (%d)", ret);
                }
            }
        }
    }
}

static const MemoryRegionOps assigned_dev_msix_mmio_ops = {
    .read = assigned_dev_msix_mmio_read,
    .write = assigned_dev_msix_mmio_write,
    .endianness = DEVICE_NATIVE_ENDIAN,
    .valid = {
        .min_access_size = 4,
        .max_access_size = 8,
    },
    .impl = {
        .min_access_size = 4,
        .max_access_size = 8,
    },
};

static void assigned_dev_msix_reset(AssignedDevice *dev)
{
    MSIXTableEntry *entry;
    int i;

    if (!dev->msix_table) {
        return;
    }

    memset(dev->msix_table, 0, MSIX_PAGE_SIZE);

    for (i = 0, entry = dev->msix_table; i < dev->msix_max; i++, entry++) {
        entry->ctrl = cpu_to_le32(0x1); /* Masked */
    }
}

static int assigned_dev_register_msix_mmio(AssignedDevice *dev)
{
    dev->msix_table = mmap(NULL, MSIX_PAGE_SIZE, PROT_READ|PROT_WRITE,
                           MAP_ANONYMOUS|MAP_PRIVATE, 0, 0);
    if (dev->msix_table == MAP_FAILED) {
        error_report("fail allocate msix_table! %s", strerror(errno));
        return -EFAULT;
    }

    assigned_dev_msix_reset(dev);

    memory_region_init_io(&dev->mmio, OBJECT(dev), &assigned_dev_msix_mmio_ops,
                          dev, "assigned-dev-msix", MSIX_PAGE_SIZE);
    return 0;
}

static void assigned_dev_unregister_msix_mmio(AssignedDevice *dev)
{
    if (!dev->msix_table) {
        return;
    }

    memory_region_destroy(&dev->mmio);

    if (munmap(dev->msix_table, MSIX_PAGE_SIZE) == -1) {
        error_report("error unmapping msix_table! %s", strerror(errno));
    }
    dev->msix_table = NULL;
}

static const VMStateDescription vmstate_assigned_device = {
    .name = "pci-assign",
    .unmigratable = 1,
};

static void reset_assigned_device(DeviceState *dev)
{
    PCIDevice *pci_dev = DO_UPCAST(PCIDevice, qdev, dev);
    AssignedDevice *adev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    char reset_file[64];
    const char reset[] = "1";
    int fd, ret;

    /*
     * If a guest is reset without being shutdown, MSI/MSI-X can still
     * be running.  We want to return the device to a known state on
     * reset, so disable those here.  We especially do not want MSI-X
     * enabled since it lives in MMIO space, which is about to get
     * disabled.
     */
    if (adev->assigned_irq_type == ASSIGNED_IRQ_MSIX) {
        uint16_t ctrl = pci_get_word(pci_dev->config +
                                     pci_dev->msix_cap + PCI_MSIX_FLAGS);

        pci_set_word(pci_dev->config + pci_dev->msix_cap + PCI_MSIX_FLAGS,
                     ctrl & ~PCI_MSIX_FLAGS_ENABLE);
        assigned_dev_update_msix(pci_dev);
    } else if (adev->assigned_irq_type == ASSIGNED_IRQ_MSI) {
        uint8_t ctrl = pci_get_byte(pci_dev->config +
                                    pci_dev->msi_cap + PCI_MSI_FLAGS);

        pci_set_byte(pci_dev->config + pci_dev->msi_cap + PCI_MSI_FLAGS,
                     ctrl & ~PCI_MSI_FLAGS_ENABLE);
        assigned_dev_update_msi(pci_dev);
    }

    snprintf(reset_file, sizeof(reset_file),
             "/sys/bus/pci/devices/%04x:%02x:%02x.%01x/reset",
             adev->host.domain, adev->host.bus, adev->host.slot,
             adev->host.function);

    /*
     * Issue a device reset via pci-sysfs.  Note that we use write(2) here
     * and ignore the return value because some kernels have a bug that
     * returns 0 rather than bytes written on success, sending us into an
     * infinite retry loop using other write mechanisms.
     */
    fd = open(reset_file, O_WRONLY);
    if (fd != -1) {
        ret = write(fd, reset, strlen(reset));
        (void)ret;
        close(fd);
    }

    /*
     * When a 0 is written to the bus master register, the device is logically
     * disconnected from the PCI bus. This avoids further DMA transfers.
     */
    assigned_dev_pci_write_config(pci_dev, PCI_COMMAND, 0, 1);
}

static int assigned_initfn(struct PCIDevice *pci_dev)
{
    AssignedDevice *dev = DO_UPCAST(AssignedDevice, dev, pci_dev);
    uint8_t e_intx;
    int r;

    if (!kvm_enabled()) {
        error_report("pci-assign: error: requires KVM support");
        return -1;
    }

    if (!dev->host.domain && !dev->host.bus && !dev->host.slot &&
        !dev->host.function) {
        error_report("pci-assign: error: no host device specified");
        return -1;
    }

    /*
     * Set up basic config space access control. Will be further refined during
     * device initialization.
     */
    assigned_dev_emulate_config_read(dev, 0, PCI_CONFIG_SPACE_SIZE);
    assigned_dev_direct_config_read(dev, PCI_STATUS, 2);
    assigned_dev_direct_config_read(dev, PCI_REVISION_ID, 1);
    assigned_dev_direct_config_read(dev, PCI_CLASS_PROG, 3);
    assigned_dev_direct_config_read(dev, PCI_CACHE_LINE_SIZE, 1);
    assigned_dev_direct_config_read(dev, PCI_LATENCY_TIMER, 1);
    assigned_dev_direct_config_read(dev, PCI_BIST, 1);
    assigned_dev_direct_config_read(dev, PCI_CARDBUS_CIS, 4);
    assigned_dev_direct_config_read(dev, PCI_SUBSYSTEM_VENDOR_ID, 2);
    assigned_dev_direct_config_read(dev, PCI_SUBSYSTEM_ID, 2);
    assigned_dev_direct_config_read(dev, PCI_CAPABILITY_LIST + 1, 7);
    assigned_dev_direct_config_read(dev, PCI_MIN_GNT, 1);
    assigned_dev_direct_config_read(dev, PCI_MAX_LAT, 1);
    memcpy(dev->emulate_config_write, dev->emulate_config_read,
           sizeof(dev->emulate_config_read));

    if (get_real_device(dev, dev->host.domain, dev->host.bus,
                        dev->host.slot, dev->host.function)) {
        error_report("pci-assign: Error: Couldn't get real device (%s)!",
                     dev->dev.qdev.id);
        goto out;
    }

    if (assigned_device_pci_cap_init(pci_dev) < 0) {
        goto out;
    }

    /* intercept MSI-X entry page in the MMIO */
    if (dev->cap.available & ASSIGNED_DEVICE_CAP_MSIX) {
        if (assigned_dev_register_msix_mmio(dev)) {
            goto out;
        }
    }

    /* handle real device's MMIO/PIO BARs */
    if (assigned_dev_register_regions(dev->real_device.regions,
                                      dev->real_device.region_number,
                                      dev)) {
        goto out;
    }

    /* handle interrupt routing */
    e_intx = dev->dev.config[PCI_INTERRUPT_PIN] - 1;
    dev->intpin = e_intx;
    dev->intx_route.mode = PCI_INTX_DISABLED;
    dev->intx_route.irq = -1;

    /* assign device to guest */
    r = assign_device(dev);
    if (r < 0) {
        goto out;
    }

    /* assign legacy INTx to the device */
    r = assign_intx(dev);
    if (r < 0) {
        goto assigned_out;
    }

    assigned_dev_load_option_rom(dev);

    add_boot_device_path(dev->bootindex, &pci_dev->qdev, NULL);

    return 0;

assigned_out:
    deassign_device(dev);
out:
    free_assigned_device(dev);
    return -1;
}

static void assigned_exitfn(struct PCIDevice *pci_dev)
{
    AssignedDevice *dev = DO_UPCAST(AssignedDevice, dev, pci_dev);

    deassign_device(dev);
    free_assigned_device(dev);
}

static Property assigned_dev_properties[] = {
    DEFINE_PROP_PCI_HOST_DEVADDR("host", AssignedDevice, host),
    DEFINE_PROP_BIT("prefer_msi", AssignedDevice, features,
                    ASSIGNED_DEVICE_PREFER_MSI_BIT, false),
    DEFINE_PROP_BIT("share_intx", AssignedDevice, features,
                    ASSIGNED_DEVICE_SHARE_INTX_BIT, true),
    DEFINE_PROP_INT32("bootindex", AssignedDevice, bootindex, -1),
    DEFINE_PROP_STRING("configfd", AssignedDevice, configfd_name),
    DEFINE_PROP_END_OF_LIST(),
};

static void assign_class_init(ObjectClass *klass, void *data)
{
    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
    DeviceClass *dc = DEVICE_CLASS(klass);

    k->init         = assigned_initfn;
    k->exit         = assigned_exitfn;
    k->config_read  = assigned_dev_pci_read_config;
    k->config_write = assigned_dev_pci_write_config;
    dc->props       = assigned_dev_properties;
    dc->vmsd        = &vmstate_assigned_device;
    dc->reset       = reset_assigned_device;
    dc->desc        = "KVM-based PCI passthrough";
}

static const TypeInfo assign_info = {
    .name               = "kvm-pci-assign",
    .parent             = TYPE_PCI_DEVICE,
    .instance_size      = sizeof(AssignedDevice),
    .class_init         = assign_class_init,
};

static void assign_register_types(void)
{
    type_register_static(&assign_info);
}

type_init(assign_register_types)

/*
 * Scan the assigned devices for the devices that have an option ROM, and then
 * load the corresponding ROM data to RAM. If an error occurs while loading an
 * option ROM, we just ignore that option ROM and continue with the next one.
 */
static void assigned_dev_load_option_rom(AssignedDevice *dev)
{
    char name[32], rom_file[64];
    FILE *fp;
    uint8_t val;
    struct stat st;
    void *ptr;

    /* If loading ROM from file, pci handles it */
    if (dev->dev.romfile || !dev->dev.rom_bar) {
        return;
    }

    snprintf(rom_file, sizeof(rom_file),
             "/sys/bus/pci/devices/%04x:%02x:%02x.%01x/rom",
             dev->host.domain, dev->host.bus, dev->host.slot,
             dev->host.function);

    if (stat(rom_file, &st)) {
        return;
    }

    if (access(rom_file, F_OK)) {
        error_report("pci-assign: Insufficient privileges for %s", rom_file);
        return;
    }

    /* Write "1" to the ROM file to enable it */
    fp = fopen(rom_file, "r+");
    if (fp == NULL) {
        return;
    }
    val = 1;
    if (fwrite(&val, 1, 1, fp) != 1) {
        goto close_rom;
    }
    fseek(fp, 0, SEEK_SET);

    snprintf(name, sizeof(name), "%s.rom",
            object_get_typename(OBJECT(dev)));
    memory_region_init_ram(&dev->dev.rom, OBJECT(dev), name, st.st_size);
    vmstate_register_ram(&dev->dev.rom, &dev->dev.qdev);
    ptr = memory_region_get_ram_ptr(&dev->dev.rom);
    memset(ptr, 0xff, st.st_size);

    if (!fread(ptr, 1, st.st_size, fp)) {
        error_report("pci-assign: Cannot read from host %s", rom_file);
        error_printf("Device option ROM contents are probably invalid "
                     "(check dmesg).\nSkip option ROM probe with rombar=0, "
                     "or load from file with romfile=\n");
        memory_region_destroy(&dev->dev.rom);
        goto close_rom;
    }

    pci_register_bar(&dev->dev, PCI_ROM_SLOT, 0, &dev->dev.rom);
    dev->dev.has_rom = true;
close_rom:
    /* Write "0" to disable ROM */
    fseek(fp, 0, SEEK_SET);
    val = 0;
    if (!fwrite(&val, 1, 1, fp)) {
        DEBUG("%s\n", "Failed to disable pci-sysfs rom file");
    }
    fclose(fp);
}